Demand Response for Home Energy Management Using Reinforcement Learning and Artificial Neural Network

By Renzhi Lu, Seung Ho Hong, Mengmeng Yu. IEEE Transactions on Smart Grid, 2019

334 citations recorded by the source corpus.

Ever-changing variables in the electricity market require energy management systems (EMSs) to make optimal real-time decisions adaptively. Demand response (DR) is the latest approach being used to accelerate the efficiency and stability of power systems. This paper proposes an hour-ahead DR algorithm for home EMSs. To deal with the uncertainty in future prices, a steady price prediction model based on artificial neural network is presented. In cooperation with forecasted future prices, multi-agent reinforcement learning is adopted to make optimal decisions for different home appliances in a decentralized manner. To verify the performance of the proposed energy management scheme, simulations are conducted with non-shiftable, shiftable, and controllable loads. Experimental results demonstrate that the proposed DR algorithm can handle energy management for multiple appliances, minimize user energy bills, and dissatisfaction costs, and help the user to significantly reduce its electricity cost compared with a benchmark without DR.

Subfields: Electrical and Electronic Engineering, Renewable Energy, Sustainability and the Environment

View Paper: https://www.semanticscholar.org/paper/4ebbd178639ed31e6ca1eac7ff0fe17bcb1d1090

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Na Li
2. Steven H. Low
3. Yujie Tang
4. Zhe Chen
5. Frede Blaabjerg
6. Xin Chen
7. Guannan Qu
8. X. Guan

In Renewable Energy, Sustainability and the Environment

1. Frede Blaabjerg
2. Tao Jiang
3. Chun Sing Lai

Citations in the corpus

• Deep Reinforcement Learning for Smart Home Energy Management (2019, methodology): “For example, Lu et al. in [12] proposed an energy management scheme to minimize the sum of electricity cost and user dissatisfaction cost associated with wash machines and HVAC loads based on multi-agent reinforcement learning and artificial neural network approach.”
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges (2021, background): “In [104], [133]–[135], DRL-based HEMS is developed to optimally schedule household electric appliances, considering resident’s preferences, uncertain electricity price and weather conditions.”
• A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management (2020, methodology): “Reference [16] proposes an hour-ahead DR algorithm to make optimal decisions for different home appliances.”
• Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review (2020, methodology): “Reference [105] applies multiple Q-learning agents to deal with the decision-making problem of multiple home appliances.”
• A Review of Deep Reinforcement Learning for Smart Building Energy Management (2020, background): “, the learned policy is different from the behavior policy used f r selecting actions [69]) ma ne , which means that th previou colle ted experience transitions in the same environment can be used f r training.”